E-LIB Suche - Ergebnisse für: Kwon, Youngki

1

Advancing the Dimensionality Reduction of Speaker Embedding..:

, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Kim, You Jin ; Heo, Hee-Soo ; Jung, Jee-Weon... - p. 1-5 , 2023

Link: https://doi.org/10.1109/..

2

Absolute Decision Corrupts Absolutely: Conservative Online ..:

, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Kwon, Youngki ; Heo, Hee-Soo ; Lee, Bong-Jin.. - p. 1-5 , 2023

Link: https://doi.org/10.1109/..

3

In Search of Strong Embedding Extractors for Speaker Diaris..:

, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Jung, Jee-Weon ; Heo, Hee-Soo ; Lee, Bong-Jin... - p. 1-5 , 2023

Link: https://doi.org/10.1109/..

4

High-Resolution Embedding Extractor for Speaker Diarisation:

, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Heo, Hee-Soo ; Kwon, Youngki ; Lee, Bong-Jin.. - p. 1-5 , 2023

Link: https://doi.org/10.1109/..

5

Multi-Scale Speaker Embedding-Based Graph Attention Network..:

, In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Kwon, Youngki ; Heo, Hee-Soo ; Jung, Jee-Weon... - p. 8367-8371 , 2022

Link: https://doi.org/10.1109/..

6

Improved Ohmic Contact by Pre‐Metallization Annealing Proce..:

Mun, Ha Jin ; Hwang, Ji Hyun ; Kwon, Young‐Ki..
physica status solidi (a). 215 (2018) 8 - p. , 2018

Link: https://doi.org/10.1002/..

7

Vasorelaxant effects of Angelica decursiva root on isolated..:

Kim, Bumjung ; Kwon, Youngki ; Lee, Somin...
BMC Complementary and Alternative Medicine. 17 (2017) 1 - p. , 2017

Link: https://doi.org/10.1186/..

8

Rethinking Session Variability: Leveraging Session Embeddin..:

Heo, Hee-Soo ; Nam, KiHyun ; Lee, Bong-Jin...
http://arxiv.org/abs/2309.14741. , 2023

Link: http://arxiv.org/abs/230..

9

Encoder-decoder multimodal speaker change detection:

Jung, Jee-weon ; Seo, Soonshin ; Heo, Hee-Soo...
http://arxiv.org/abs/2306.00680. , 2023

Link: http://arxiv.org/abs/230..

10

High-resolution embedding extractor for speaker diarisation:

Heo, Hee-Soo ; Kwon, Youngki ; Lee, Bong-Jin..
http://arxiv.org/abs/2211.04060. , 2022

Link: http://arxiv.org/abs/221..

11

Pushing the limits of raw waveform speaker recognition:

Jung, Jee-weon ; Kim, You Jin ; Heo, Hee-Soo...
http://arxiv.org/abs/2203.08488. , 2022

Link: http://arxiv.org/abs/220..

12

Curriculum learning for self-supervised speaker verificatio:

Heo, Hee-Soo ; Jung, Jee-weon ; Kang, Jingu...
http://arxiv.org/abs/2203.14525. , 2022

Link: http://arxiv.org/abs/220..

13

Absolute decision corrupts absolutely: conservative online ..:

Kwon, Youngki ; Heo, Hee-Soo ; Lee, Bong-Jin..
http://arxiv.org/abs/2211.04768. , 2022

Link: http://arxiv.org/abs/221..

14

Large-scale learning of generalised representations for spe..:

Jung, Jee-weon ; Heo, Hee-Soo ; Lee, Bong-Jin...
http://arxiv.org/abs/2210.10985. , 2022

Link: http://arxiv.org/abs/221..

15

In search of strong embedding extractors for speaker diaris..:

Jung, Jee-weon ; Heo, Hee-Soo ; Lee, Bong-Jin...
http://arxiv.org/abs/2210.14682. , 2022

Link: http://arxiv.org/abs/221..